Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    cooking until

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.43
    the
    0.42
    with
    0.41
     যাদ
    0.41
    м
    0.40
    дите
    0.38
     ด้วย
    0.38
     文件
    0.38
    文件
    0.38
     一
    0.37
    POSITIVE LOGITS
     encourages
    0.43
    amerikanischer
    0.41
     internships
    0.41
     emphasises
    0.41
     motivations
    0.41
     अस्पताल
    0.40
     orthogonal
    0.39
     covariates
    0.39
     davranış
    0.39
    hôpital
    0.38
    Act Density 0.002%

    No Known Activations